Metraipolis › archive › dc_ddecda7910cb

DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention — arXiv:2610.41994

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41994
License (as archived): CC0-1.0
Archived: 2026-11-03T07:12:13.135Z
SHA-256 of the archived text: 095dbd76b4aa63a2f2ba6f4311d8c3dd4bd6628a860b31ae6b2d3bdb6ff46489
Stable URL of this page: https://metraipolis.com/documento/dc_ddecda7910cb

How to cite

DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention — arXiv:2610.41994 — arXiv (en), https://arxiv.org/abs/2610.41994 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ddecda7910cb (Metraipolis archive dc_ddecda7910cb, sha256 095dbd76b4aa63a2f2ba6f4311d8c3dd4bd6628a860b31ae6b2d3bdb6ff46489)

BibTeX

@misc{dcddecda7910cb,
  title = {DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention — arXiv:2610.41994},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41994},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ddecda7910cb; sha256 095dbd76b4aa63a2f2ba6f4311d8c3dd4bd6628a860b31ae6b2d3bdb6ff46489},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41994. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In gated linear recurrences, memory retention depends on state decay, which is shaped jointly by gate parameters A_log and dt_bias and by input activations. In controlled Gated DeltaNet (GDN) experiments, both parameters remain highly correlated with their initial values after training, highlighting the importance of initialization. Therefore, we introduce Dual-Axis Memory Initialization (DAMI), which jointly configures these parameters before training. DAMI assigns geometric timescales across heads for varied retrieval distances and a low-high-low input-sensitivity profile across layers. A small activation sample calibrates the GDN-family implementation to match both behavioral targets without adding trainable parameters. Across GDN, KDA, GDN2, Mamba-2, and RWKV-7, DAMI improves average RULER-style retrieval accuracy by 5.29 to 16.71 percentage points over the corresponding random-initialization baselines. Performance on language modeling, commonsense reasoning, and 2K real-world retrieval remains broadly comparable to those baselines. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41994 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:09:31.805Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).